update plr page highlighting

Author: SvenKlaassen

doc/plm/plr.qmd

@@ -10,54 +10,16 @@ jupyter: python3
 import numpy as np
 import pandas as pd
 from itables import init_notebook_mode, show, options
+import os
+import sys
 
-init_notebook_mode(all_interactive=True)
+doc_dir = os.path.abspath(os.path.join(os.getcwd(), ".."))
+if doc_dir not in sys.path:
+    sys.path.append(doc_dir)
+
+from utils.style_tables import create_styled_table
 
-def highlight_range(s, level=0.95, dist=0.05, props=''):
-    color_grid = np.where((s >= level-dist) &
-                          (s <= level+dist), props, '')
-    return color_grid
-
-
-def color_coverage(df, level):
-    # color coverage column order is important
-    styled_df = df.apply(
-        highlight_range,
-        level=level,
-        dist=1.0,
-        props='color:black;background-color:red',
-        subset=["Coverage"])
-    styled_df = styled_df.apply(
-        highlight_range,
-        level=level,
-        dist=0.1,
-        props='color:black;background-color:yellow',
-        subset=["Coverage"])
-    styled_df = styled_df.apply(
-        highlight_range,
-        level=level,
-        dist=0.05,
-        props='color:white;background-color:darkgreen',
-        subset=["Coverage"])
-
-    # set all coverage values to bold
-    styled_df = styled_df.set_properties(
-        **{'font-weight': 'bold'},
-        subset=["Coverage"])
-    return styled_df
-
-
-def make_pretty(df, level, n_rep):
-    styled_df = df.style.hide(axis="index")
-    # Format only float columns
-    float_cols = df.select_dtypes(include=['float']).columns
-    styled_df = styled_df.format({col: "{:.3f}" for col in float_cols})
-
-    # color coverage column order is important
-    styled_df = color_coverage(styled_df, level)
-    caption = f"Coverage for {level*100}%-Confidence Interval over {n_rep} Repetitions"
-
-    return show(styled_df, caption=caption, allow_html=True)
+init_notebook_mode(all_interactive=True)
 ```
 
 ## ATE Coverage
@@ -79,34 +41,41 @@ print(metadata_df.T.to_string(header=False))
 #| echo: false
 
 # set up data and rename columns
-df = pd.read_csv("../../results/plm/plr_ate_coverage.csv", index_col=None)
+df_coverage = pd.read_csv("../../results/plm/plr_ate_coverage.csv", index_col=None)
 
-assert df["repetition"].nunique() == 1
-n_rep = df["repetition"].unique()[0]
+if "repetition" in df_coverage.columns and df_coverage["repetition"].nunique() == 1:
+    n_rep_coverage = df_coverage["repetition"].unique()[0]
+elif "n_rep" in df_coverage.columns and df_coverage["n_rep"].nunique() == 1:
+    n_rep_coverage = df_coverage["n_rep"].unique()[0]
+else:
+    n_rep_coverage = "N/A" # Fallback if n_rep cannot be determined
 
-display_columns = ["Learner g", "Learner m", "Bias", "CI Length", "Coverage"]
+display_columns_coverage = ["Learner g", "Learner m", "Bias", "CI Length", "Coverage"]
 ```
 
 ### Partialling out
 
 ```{python}
 # | echo: false
-score = "partialling out"
-level = 0.95
+score_po = "partialling out"
+level_95 = 0.95
 
-df_ate_95 = df[(df["level"] == level) & (df["score"] == score)][display_columns]
-df_ate_95.rename(columns={"Learner g": "Learner l"}, inplace=True)
-make_pretty(df_ate_95, level, n_rep)
+df_po_95 = df_coverage[(df_coverage["level"] == level_95) & (df_coverage["score"] == score_po)][display_columns_coverage].copy()
+df_po_95.rename(columns={"Learner g": "Learner l"}, inplace=True)
+
+styled_table_po_95 = create_styled_table(df_po_95, level_95, n_rep_coverage, coverage_cols=["Coverage"])
+show(styled_table_po_95, allow_html=True)
 ```
 
 ```{python}
 #| echo: false
-score = "partialling out"
-level = 0.9
+level_90 = 0.9
+
+df_po_90 = df_coverage[(df_coverage['level'] == level_90) & (df_coverage["score"] == score_po)][display_columns_coverage].copy()
+df_po_90.rename(columns={"Learner g": "Learner l"}, inplace=True)
 
-df_ate_9 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-df_ate_9.rename(columns={"Learner g": "Learner l"}, inplace=True)
-make_pretty(df_ate_9, level, n_rep)
+styled_table_po_90 = create_styled_table(df_po_90, level_90, n_rep_coverage, coverage_cols=["Coverage"])
+show(styled_table_po_90, allow_html=True)
 ```
 
 ### IV-type
@@ -115,20 +84,23 @@ For the IV-type score, the learners `ml_l` and `ml_g` are both set to the same t
 
 ```{python}
 #| echo: false
-score = "IV-type"
-level = 0.95
+score_iv = "IV-type"
+# level_95 is already defined
+
+df_iv_95 = df_coverage[(df_coverage['level'] == level_95) & (df_coverage["score"] == score_iv)][display_columns_coverage]
 
-df_ate_95 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-make_pretty(df_ate_95, level, n_rep)
+styled_table_iv_95 = create_styled_table(df_iv_95, level_95, n_rep_coverage, coverage_cols=["Coverage"])
+show(styled_table_iv_95, allow_html=True)
 ```
 
 ```{python}
 #| echo: false
-score = "IV-type"
-level = 0.9
+# level_90 is already defined
 
-df_ate_9 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-make_pretty(df_ate_9, level, n_rep)
+df_iv_90 = df_coverage[(df_coverage['level'] == level_90) & (df_coverage["score"] == score_iv)][display_columns_coverage]
+
+styled_table_iv_90 = create_styled_table(df_iv_90, level_90, n_rep_coverage, coverage_cols=["Coverage"])
+show(styled_table_iv_90, allow_html=True)
 ```
 
 ## ATE Sensitivity
@@ -142,9 +114,9 @@ Further, the corresponding confidence intervals are one-sided (since the directi
 
 ```{python}
 #| echo: false
-metadata_file = '../../results/plm/plr_ate_sensitivity_metadata.csv'
-metadata_df = pd.read_csv(metadata_file)
-print(metadata_df.T.to_string(header=False))
+metadata_file_sens = '../../results/plm/plr_ate_sensitivity_metadata.csv'
+metadata_df_sens = pd.read_csv(metadata_file_sens)
+print(metadata_df_sens.T.to_string(header=False))
 ```
 
 :::
@@ -153,91 +125,52 @@ print(metadata_df.T.to_string(header=False))
 #| echo: false
 
 # set up data and rename columns
-df = pd.read_csv("../../results/plm/plr_ate_sensitivity.csv", index_col=None)
+df_sensitivity = pd.read_csv("../../results/plm/plr_ate_sensitivity.csv", index_col=None)
 
-assert df["repetition"].nunique() == 1
-n_rep = df["repetition"].unique()[0]
+if "repetition" in df_sensitivity.columns and df_sensitivity["repetition"].nunique() == 1:
+    n_rep_sensitivity = df_sensitivity["repetition"].unique()[0]
+elif "n_rep" in df_sensitivity.columns and df_sensitivity["n_rep"].nunique() == 1:
+    n_rep_sensitivity = df_sensitivity["n_rep"].unique()[0]
+else:
+    n_rep_sensitivity = "N/A"
 
-display_columns = [
+display_columns_sensitivity = [
     "Learner g", "Learner m", "Bias", "Bias (Lower)", "Bias (Upper)", "Coverage", "Coverage (Lower)", "Coverage (Upper)", "RV", "RVa"]
 ```
 
-```{python}
-#| echo: false
-
-import numpy as np
-import pandas as pd
-from itables import init_notebook_mode, show, options
-
-init_notebook_mode(all_interactive=True)
-
-def highlight_range(s, level=0.95, dist=0.05, props=''):
-    color_grid = np.where((s >= level-dist) &
-                          (s <= level+dist), props, '')
-    return color_grid
-
-
-def color_coverage(df, level):
-    # color coverage column order is important
-    styled_df = df.apply(
-        highlight_range,
-        level=level,
-        dist=1.0,
-        props='color:black;background-color:red',
-        subset=["Coverage", "Coverage (Upper)"])
-    styled_df = styled_df.apply(
-        highlight_range,
-        level=level,
-        dist=0.1,
-        props='color:black;background-color:yellow',
-        subset=["Coverage", "Coverage (Upper)"])
-    styled_df = styled_df.apply(
-        highlight_range,
-        level=level,
-        dist=0.05,
-        props='color:white;background-color:darkgreen',
-        subset=["Coverage", "Coverage (Upper)"])
-
-    # set all coverage values to bold
-    styled_df = styled_df.set_properties(
-        **{'font-weight': 'bold'},
-        subset=["Coverage", "Coverage (Upper)"])
-    return styled_df
-
-
-def make_pretty(df, level, n_rep):
-    styled_df = df.style.hide(axis="index")
-    # Format only float columns
-    float_cols = df.select_dtypes(include=['float']).columns
-    styled_df = styled_df.format({col: "{:.3f}" for col in float_cols})
-
-    # color coverage column order is important
-    styled_df = color_coverage(styled_df, level)
-    caption = f"Coverage for {level*100}%-Confidence Interval over {n_rep} Repetitions"
-
-    return show(styled_df, caption=caption, allow_html=True)
-```
 
 ### Partialling out
 
 ```{python}
 #| echo: false
-score = "partialling out"
-level = 0.95
-
-df_ate_95 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-df_ate_95.rename(columns={"Learner g": "Learner l"}, inplace=True)
-make_pretty(df_ate_95, level, n_rep)
+# score_po and level_95 are defined above
+
+df_sens_po_95 = df_sensitivity[(df_sensitivity['level'] == level_95) & (df_sensitivity["score"] == score_po)][display_columns_sensitivity].copy()
+df_sens_po_95.rename(columns={"Learner g": "Learner l"}, inplace=True)
+
+styled_sens_po_95 = create_styled_table(
+    df_sens_po_95,
+    level_95,
+    n_rep_sensitivity,
+    coverage_cols=["Coverage", "Coverage (Upper)"] # Highlight both
+)
+show(styled_sens_po_95, allow_html=True)
 ```
 
 ```{python}
 #| echo: false
-score = "partialling out"
-level = 0.9
-
-df_ate_9 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-df_ate_9.rename(columns={"Learner g": "Learner l"}, inplace=True)
-make_pretty(df_ate_9, level, n_rep)
+# score_po and level_90 are defined above
+
+df_sens_po_90 = df_sensitivity[(df_sensitivity['level'] == level_90) & (df_sensitivity["score"] == score_po)][display_columns_sensitivity].copy()
+df_sens_po_90.rename(columns={"Learner g": "Learner l"}, inplace=True)
+
+styled_sens_po_90 = create_styled_table(
+    df_sens_po_90,
+    level_90,
+    n_rep_sensitivity,
+    coverage_cols=["Coverage", "Coverage (Upper)"]
+)
+show(styled_sens_po_90, allow_html=True)
 ```
 
 ### IV-type
@@ -246,18 +179,30 @@ For the IV-type score, the learners `ml_l` and `ml_g` are both set to the same t
 
 ```{python}
 #| echo: false
-score = "IV-type"
-level = 0.95
+# score_iv and level_95 are defined above
 
-df_ate_95 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-make_pretty(df_ate_95, level, n_rep)
+df_sens_iv_95 = df_sensitivity[(df_sensitivity['level'] == level_95) & (df_sensitivity["score"] == score_iv)][display_columns_sensitivity]
+
+styled_sens_iv_95 = create_styled_table(
+    df_sens_iv_95,
+    level_95,
+    n_rep_sensitivity,
+    coverage_cols=["Coverage", "Coverage (Upper)"]
+)
+show(styled_sens_iv_95, allow_html=True)
 ```
 
 ```{python}
 #| echo: false
-score = "IV-type"
-level = 0.9
+# score_iv and level_90 are defined above
+
+df_sens_iv_90 = df_sensitivity[(df_sensitivity['level'] == level_90) & (df_sensitivity["score"] == score_iv)][display_columns_sensitivity]
 
-df_ate_9 = df[(df['level'] == level) & (df["score"] == score)][display_columns]
-make_pretty(df_ate_9, level, n_rep)
+styled_sens_iv_90 = create_styled_table(
+    df_sens_iv_90,
+    level_90,
+    n_rep_sensitivity,
+    coverage_cols=["Coverage", "Coverage (Upper)"]
+)
+show(styled_sens_iv_90, allow_html=True)
 ```